Fault diagnosis of gas turbine engines by using dynamic neural networks

2011 ◽  
Author(s):  
R. Mohammadi ◽  
E. Naderi ◽  
K. Khorasani ◽  
S. Hashtrudi-Zad
Keyword(s):  
Neural Networks ◽  
Fault Diagnosis ◽  
Gas Turbine ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Dynamic Neural Networks

Fault Diagnosis of Gas Turbine Engines by Using Dynamic Neural Networks

2010 ◽  
Author(s):  
Rasul Mohammadi ◽  
Esmaeil Naderi ◽  
Khashayar Khorasani ◽  
Shahin Hashtrudi-Zad
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Detection ◽  
Gas Turbine ◽  
Network Architecture ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Dynamic Neural Networks ◽  
Feed Forward ◽  
The Difference

This paper presents a novel methodology for fault detection in gas turbine engines based on the concept of dynamic neural networks. The neural network structure belongs to the class of locally recurrent globally feed-forward networks. The architecture of the network is similar to the feed-forward multi-layer perceptron with the difference that the processing units include dynamic characteristics. The dynamics present in these networks make them a powerful tool useful for identification of nonlinear systems. The dynamic neural network architecture that is described in this paper is used for fault detection in a dual-spool turbo fan engine. A number of simulation studies are conducted to demonstrate and verify the advantages of our proposed neural network diagnosis methodology.

Health Monitoring and Degradation Prognostics in Gas Turbine Engines Using Dynamic Neural Networks

2015 ◽  
Author(s):  
A. Vatani ◽  
K. Khorasani ◽  
N. Meskin
Keyword(s):  
Neural Network ◽  
Gas Turbine ◽  
Health Monitoring ◽  
Network Architecture ◽  
Information Criterion ◽  
Turbine Engines ◽  
Prediction Errors ◽  
Gas Turbine Engines ◽  
Dynamic Neural Networks ◽  
Turbine Engine

In this paper two artificially intelligent methodologies are proposed and developed for degradation prognosis and health monitoring of gas turbine engines. Our objective is to predict the degradation trends by studying their effects on the engine measurable parameters, such as the temperature, at critical points of the gas turbine engine. The first prognostic scheme is based on a recurrent neural network (RNN) architecture. This architecture enables ONE to learn the engine degradations from the available measurable data. The second prognostic scheme is based on a nonlinear auto-regressive with exogenous input (NARX) neural network architecture. It is shown that this network can be trained with fewer data points and the prediction errors are lower as compared to the RNN architecture. To manage prognostic and prediction uncertainties upper and lower threshold bounds are defined and obtained. Various scenarios and case studies are presented to illustrate and demonstrate the effectiveness of our proposed neural network-based prognostic approaches. To evaluate and compare the prediction results between our two proposed neural network schemes, a metric known as the normalized Akaike information criterion (NAIC) is utilized. A smaller NAIC shows a better, a more accurate and a more effective prediction outcome. The NAIC values are obtained for each case and the networks are compared relatively with one another.

Development of Fault Diagnosis and Failure Prediction Techniques for Small Gas Turbine Engines

2001 ◽  
Author(s):  
Craig R. Davison ◽  
A. M. Birk
Keyword(s):  
Fault Diagnosis ◽  
Gas Turbine ◽  
Operating Time ◽  
Turbine Engines ◽  
Time To Failure ◽  
Gas Turbine Engines ◽  
Ambient Conditions ◽  
Engine Operation ◽  
Maintenance Cycle ◽  
Prediction Techniques

A computer model of a gas turbine auxiliary power unit was produced to develop techniques for fault diagnosis and prediction of remaining life in small gas turbine engines. Due to the relatively low capital cost of small engines it is important that the techniques have both low capital and operating costs. Failing engine components were identified with fault maps, and an algorithm was developed for predicting the time to failure, based on the engine’s past operation. Simulating daily engine operation over a maintenance cycle tested the techniques for identification and prediction. The simulation included daily variations in ambient conditions, operating time, load, engine speed and operating environment, to determine the amount of degradation per day. The algorithm successfully adapted to the daily changes and corrected the operating point back to standard conditions to predict the time to failure.

Multiple-Model Sensor and Components Fault Diagnosis in Gas Turbine Engines Using Autoassociative Neural Networks

2014 ◽  
Vol 136 (9) ◽  
Author(s):  
Z. N. Sadough Vanini ◽  
N. Meskin ◽  
K. Khorasani
Keyword(s):  
Neural Networks ◽  
Fault Diagnosis ◽  
Fault Detection ◽  
Fault Detection And Isolation ◽  
Sensor Data ◽  
Turbine Engines ◽  
Multiple Model ◽  
Jet Engines ◽  
Dynamic Neural Networks ◽  
Autoassociative Neural Networks

In this paper the problem of fault diagnosis in an aircraft jet engine is investigated by using an intelligent-based methodology. The proposed fault detection and isolation (FDI) scheme is based on the multiple model approach and utilizes autoassociative neural networks (AANNs). This methodology consists of a bank of AANNs and provides a novel integrated solution to the problem of both sensor and component fault detection and isolation even though possibly both engine and sensor faults may occur concurrently. Moreover, the proposed algorithm can be used for sensor data validation and correction as the first step for health monitoring of jet engines. We have also presented a comparison between our proposed approach and another commonly used neural network scheme known as dynamic neural networks to demonstrate the advantages and capabilities of our approach. Various simulations are carried out to demonstrate the performance capabilities of our proposed fault detection and isolation scheme.

Sensor fault diagnosis of gas turbine engines using an integrated scheme based on improved least squares support vector regression

2019 ◽  
Vol 234 (3) ◽  
pp. 607-623
Author(s):  
Yu Hu ◽  
Jietang Zhu ◽  
Zhensheng Sun ◽  
Lijia Gao
Keyword(s):  
Genetic Algorithm ◽  
Fault Diagnosis ◽  
Support Vector Regression ◽  
Gas Turbine ◽  
Turbine Engines ◽  
Support Vector ◽  
Gas Turbine Engines ◽  
Sensor Fault ◽  
Diagnosis System ◽  
Fault Diagnosis System

As the flight envelope is widening continuously and operational capability is improving sequentially, gas turbine engines are faced with new challenges of increased operation and maintenance requirements for efficiency, reliability, and safety. The measures for security and safety and the need for reducing the life cycle cost make it necessary to develop more accurate and efficient monitoring and diagnostic schemes for the health management of gas turbine components. Sensors along the gas path are one of the components in gas turbines that play a crucial role in turbofan engines owing to their safety criticality. Failures in sensor measurements often result in serious problems affecting flight safety and performance. Therefore, this study aims to develop an online diagnosis system for gas path sensor faults in a turbofan engine. The fault diagnosis system is designed and implemented using a genetic algorithm optimized recursive reduced least squares support vector regression algorithm. This method uses a reduction technique and recursion strategy to obtain a better generalization performance and sparseness, and exploits an improved genetic algorithm to choose the optimal model parameters for improving the training precision. The effectiveness of the sensor fault diagnosis system is then validated through typical fault modes of single and dual sensors.

Sign in / Sign up

Export Citation Format

Share Document